DEFINE_PER_CPU(struct flush_queue, flush_queue);
+static atomic_t queue_timer_on;
+static struct timer_list queue_timer;
+
/*
* Domain for untranslated devices - only allocated
* if iommu=pt passed on kernel cmd line.
return container_of(dom, struct protection_domain, domain);
}
+static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain)
+{
+ BUG_ON(domain->flags != PD_DMA_OPS_MASK);
+ return container_of(domain, struct dma_ops_domain, domain);
+}
+
static struct iommu_dev_data *alloc_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
* Writes the command to the IOMMUs command buffer and informs the
* hardware about the new command.
*/
-static int iommu_queue_command_sync(struct amd_iommu *iommu,
- struct iommu_cmd *cmd,
- bool sync)
+static int __iommu_queue_command_sync(struct amd_iommu *iommu,
+ struct iommu_cmd *cmd,
+ bool sync)
{
u32 left, tail, head, next_tail;
- unsigned long flags;
again:
- spin_lock_irqsave(&iommu->lock, flags);
head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
if (left <= 2) {
struct iommu_cmd sync_cmd;
- volatile u64 sem = 0;
int ret;
- build_completion_wait(&sync_cmd, (u64)&sem);
- copy_cmd_to_buffer(iommu, &sync_cmd, tail);
+ iommu->cmd_sem = 0;
- spin_unlock_irqrestore(&iommu->lock, flags);
+ build_completion_wait(&sync_cmd, (u64)&iommu->cmd_sem);
+ copy_cmd_to_buffer(iommu, &sync_cmd, tail);
- if ((ret = wait_on_sem(&sem)) != 0)
+ if ((ret = wait_on_sem(&iommu->cmd_sem)) != 0)
return ret;
goto again;
/* We need to sync now to make sure all commands are processed */
iommu->need_sync = sync;
+ return 0;
+}
+
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+ struct iommu_cmd *cmd,
+ bool sync)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&iommu->lock, flags);
+ ret = __iommu_queue_command_sync(iommu, cmd, sync);
spin_unlock_irqrestore(&iommu->lock, flags);
- return 0;
+ return ret;
}
static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
static int iommu_completion_wait(struct amd_iommu *iommu)
{
struct iommu_cmd cmd;
- volatile u64 sem = 0;
+ unsigned long flags;
int ret;
if (!iommu->need_sync)
return 0;
- build_completion_wait(&cmd, (u64)&sem);
- ret = iommu_queue_command_sync(iommu, &cmd, false);
+ build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+
+ iommu->cmd_sem = 0;
+
+ ret = __iommu_queue_command_sync(iommu, &cmd, false);
if (ret)
- return ret;
+ goto out_unlock;
+
+ ret = wait_on_sem(&iommu->cmd_sem);
- return wait_on_sem(&sem);
+out_unlock:
+ spin_unlock_irqrestore(&iommu->lock, flags);
+
+ return ret;
}
static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
if (protection_domain_init(&dma_dom->domain))
goto free_dma_dom;
- dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
+ dma_dom->domain.mode = PAGE_MODE_3_LEVEL;
dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
dma_dom->domain.flags = PD_DMA_OPS_MASK;
- dma_dom->domain.priv = dma_dom;
if (!dma_dom->domain.pt_root)
goto free_dma_dom;
queue->next = 0;
}
+static void queue_flush_all(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct flush_queue *queue;
+ unsigned long flags;
+
+ queue = per_cpu_ptr(&flush_queue, cpu);
+ spin_lock_irqsave(&queue->lock, flags);
+ if (queue->next > 0)
+ __queue_flush(queue);
+ spin_unlock_irqrestore(&queue->lock, flags);
+ }
+}
+
+static void queue_flush_timeout(unsigned long unsused)
+{
+ atomic_set(&queue_timer_on, 0);
+ queue_flush_all();
+}
+
static void queue_add(struct dma_ops_domain *dma_dom,
unsigned long address, unsigned long pages)
{
entry->dma_dom = dma_dom;
spin_unlock_irqrestore(&queue->lock, flags);
+
+ if (atomic_cmpxchg(&queue_timer_on, 0, 1) == 0)
+ mod_timer(&queue_timer, jiffies + msecs_to_jiffies(10));
+
put_cpu_ptr(&flush_queue);
}
static struct protection_domain *get_domain(struct device *dev)
{
struct protection_domain *domain;
- struct iommu_domain *io_domain;
if (!check_device(dev))
return ERR_PTR(-EINVAL);
- io_domain = iommu_get_domain_for_dev(dev);
- if (!io_domain)
- return NULL;
-
- domain = to_pdomain(io_domain);
+ domain = get_dev_data(dev)->domain;
if (!dma_ops_domain(domain))
return ERR_PTR(-EBUSY);
{
struct iommu_dev_data *dev_data;
- list_for_each_entry(dev_data, &domain->dev_list, list)
+ list_for_each_entry(dev_data, &domain->dev_list, list) {
set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+
+ if (dev_data->devid == dev_data->alias)
+ continue;
+
+ /* There is an alias, update device table entry for it */
+ set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled);
+ }
}
static void update_domain(struct protection_domain *domain)
domain->updated = false;
}
+static int dir2prot(enum dma_data_direction direction)
+{
+ if (direction == DMA_TO_DEVICE)
+ return IOMMU_PROT_IR;
+ else if (direction == DMA_FROM_DEVICE)
+ return IOMMU_PROT_IW;
+ else if (direction == DMA_BIDIRECTIONAL)
+ return IOMMU_PROT_IW | IOMMU_PROT_IR;
+ else
+ return 0;
+}
/*
* This function contains common code for mapping of a physically
* contiguous memory region into DMA address space. It is used by all
struct dma_ops_domain *dma_dom,
phys_addr_t paddr,
size_t size,
- int direction,
+ enum dma_data_direction direction,
u64 dma_mask)
{
dma_addr_t offset = paddr & ~PAGE_MASK;
if (address == DMA_ERROR_CODE)
goto out;
- if (direction == DMA_TO_DEVICE)
- prot = IOMMU_PROT_IR;
- else if (direction == DMA_FROM_DEVICE)
- prot = IOMMU_PROT_IW;
- else if (direction == DMA_BIDIRECTIONAL)
- prot = IOMMU_PROT_IW | IOMMU_PROT_IR;
+ prot = dir2prot(direction);
start = address;
for (i = 0; i < pages; ++i) {
static dma_addr_t map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ unsigned long attrs)
{
phys_addr_t paddr = page_to_phys(page) + offset;
struct protection_domain *domain;
+ struct dma_ops_domain *dma_dom;
u64 dma_mask;
domain = get_domain(dev);
return DMA_ERROR_CODE;
dma_mask = *dev->dma_mask;
+ dma_dom = to_dma_ops_domain(domain);
- return __map_single(dev, domain->priv, paddr, size, dir, dma_mask);
+ return __map_single(dev, dma_dom, paddr, size, dir, dma_mask);
}
/*
* The exported unmap_single function for dma_ops.
*/
static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
- enum dma_data_direction dir, struct dma_attrs *attrs)
+ enum dma_data_direction dir, unsigned long attrs)
{
struct protection_domain *domain;
+ struct dma_ops_domain *dma_dom;
domain = get_domain(dev);
if (IS_ERR(domain))
return;
- __unmap_single(domain->priv, dma_addr, size, dir);
+ dma_dom = to_dma_ops_domain(domain);
+
+ __unmap_single(dma_dom, dma_addr, size, dir);
+}
+
+static int sg_num_pages(struct device *dev,
+ struct scatterlist *sglist,
+ int nelems)
+{
+ unsigned long mask, boundary_size;
+ struct scatterlist *s;
+ int i, npages = 0;
+
+ mask = dma_get_seg_boundary(dev);
+ boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
+ 1UL << (BITS_PER_LONG - PAGE_SHIFT);
+
+ for_each_sg(sglist, s, nelems, i) {
+ int p, n;
+
+ s->dma_address = npages << PAGE_SHIFT;
+ p = npages % boundary_size;
+ n = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
+ if (p + n > boundary_size)
+ npages += boundary_size - p;
+ npages += n;
+ }
+
+ return npages;
}
/*
* lists).
*/
static int map_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ int nelems, enum dma_data_direction direction,
+ unsigned long attrs)
{
+ int mapped_pages = 0, npages = 0, prot = 0, i;
struct protection_domain *domain;
- int i;
+ struct dma_ops_domain *dma_dom;
struct scatterlist *s;
- phys_addr_t paddr;
- int mapped_elems = 0;
+ unsigned long address;
u64 dma_mask;
domain = get_domain(dev);
if (IS_ERR(domain))
return 0;
+ dma_dom = to_dma_ops_domain(domain);
dma_mask = *dev->dma_mask;
+ npages = sg_num_pages(dev, sglist, nelems);
+
+ address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask);
+ if (address == DMA_ERROR_CODE)
+ goto out_err;
+
+ prot = dir2prot(direction);
+
+ /* Map all sg entries */
for_each_sg(sglist, s, nelems, i) {
- paddr = sg_phys(s);
+ int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
+
+ for (j = 0; j < pages; ++j) {
+ unsigned long bus_addr, phys_addr;
+ int ret;
- s->dma_address = __map_single(dev, domain->priv,
- paddr, s->length, dir, dma_mask);
+ bus_addr = address + s->dma_address + (j << PAGE_SHIFT);
+ phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
+ ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC);
+ if (ret)
+ goto out_unmap;
- if (s->dma_address) {
- s->dma_length = s->length;
- mapped_elems++;
- } else
- goto unmap;
+ mapped_pages += 1;
+ }
+ }
+
+ /* Everything is mapped - write the right values into s->dma_address */
+ for_each_sg(sglist, s, nelems, i) {
+ s->dma_address += address + s->offset;
+ s->dma_length = s->length;
}
- return mapped_elems;
+ return nelems;
+
+out_unmap:
+ pr_err("%s: IOMMU mapping error in map_sg (io-pages: %d)\n",
+ dev_name(dev), npages);
+
+ for_each_sg(sglist, s, nelems, i) {
+ int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
-unmap:
- for_each_sg(sglist, s, mapped_elems, i) {
- if (s->dma_address)
- __unmap_single(domain->priv, s->dma_address,
- s->dma_length, dir);
- s->dma_address = s->dma_length = 0;
+ for (j = 0; j < pages; ++j) {
+ unsigned long bus_addr;
+
+ bus_addr = address + s->dma_address + (j << PAGE_SHIFT);
+ iommu_unmap_page(domain, bus_addr, PAGE_SIZE);
+
+ if (--mapped_pages)
+ goto out_free_iova;
+ }
}
+out_free_iova:
+ free_iova_fast(&dma_dom->iovad, address, npages);
+
+out_err:
return 0;
}
*/
static void unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction dir,
- struct dma_attrs *attrs)
+ unsigned long attrs)
{
struct protection_domain *domain;
- struct scatterlist *s;
- int i;
+ struct dma_ops_domain *dma_dom;
+ unsigned long startaddr;
+ int npages = 2;
domain = get_domain(dev);
if (IS_ERR(domain))
return;
- for_each_sg(sglist, s, nelems, i) {
- __unmap_single(domain->priv, s->dma_address,
- s->dma_length, dir);
- s->dma_address = s->dma_length = 0;
- }
+ startaddr = sg_dma_address(sglist) & PAGE_MASK;
+ dma_dom = to_dma_ops_domain(domain);
+ npages = sg_num_pages(dev, sglist, nelems);
+
+ __unmap_single(dma_dom, startaddr, npages << PAGE_SHIFT, dir);
}
/*
*/
static void *alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag,
- struct dma_attrs *attrs)
+ unsigned long attrs)
{
u64 dma_mask = dev->coherent_dma_mask;
struct protection_domain *domain;
+ struct dma_ops_domain *dma_dom;
struct page *page;
domain = get_domain(dev);
} else if (IS_ERR(domain))
return NULL;
+ dma_dom = to_dma_ops_domain(domain);
size = PAGE_ALIGN(size);
dma_mask = dev->coherent_dma_mask;
flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
if (!dma_mask)
dma_mask = *dev->dma_mask;
- *dma_addr = __map_single(dev, domain->priv, page_to_phys(page),
+ *dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
size, DMA_BIDIRECTIONAL, dma_mask);
if (*dma_addr == DMA_ERROR_CODE)
*/
static void free_coherent(struct device *dev, size_t size,
void *virt_addr, dma_addr_t dma_addr,
- struct dma_attrs *attrs)
+ unsigned long attrs)
{
struct protection_domain *domain;
+ struct dma_ops_domain *dma_dom;
struct page *page;
page = virt_to_page(virt_addr);
if (IS_ERR(domain))
goto free_mem;
- __unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
+ dma_dom = to_dma_ops_domain(domain);
+
+ __unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
free_mem:
if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
int __init amd_iommu_init_dma_ops(void)
{
+ setup_timer(&queue_timer, queue_flush_timeout, 0);
+ atomic_set(&queue_timer_on, 0);
+
swiotlb = iommu_pass_through ? 1 : 0;
iommu_detected = 1;
static void amd_iommu_domain_free(struct iommu_domain *dom)
{
struct protection_domain *domain;
-
- if (!dom)
- return;
+ struct dma_ops_domain *dma_dom;
domain = to_pdomain(dom);
BUG_ON(domain->dev_cnt != 0);
- if (domain->mode != PAGE_MODE_NONE)
- free_pagetable(domain);
+ if (!dom)
+ return;
- if (domain->flags & PD_IOMMUV2_MASK)
- free_gcr3_table(domain);
+ switch (dom->type) {
+ case IOMMU_DOMAIN_DMA:
+ /*
+ * First make sure the domain is no longer referenced from the
+ * flush queue
+ */
+ queue_flush_all();
+
+ /* Now release the domain */
+ dma_dom = to_dma_ops_domain(domain);
+ dma_ops_domain_free(dma_dom);
+ break;
+ default:
+ if (domain->mode != PAGE_MODE_NONE)
+ free_pagetable(domain);
- protection_domain_free(domain);
+ if (domain->flags & PD_IOMMUV2_MASK)
+ free_gcr3_table(domain);
+
+ protection_domain_free(domain);
+ break;
+ }
}
static void amd_iommu_detach_device(struct iommu_domain *dom,
struct iommu_domain *domain,
struct iommu_dm_region *region)
{
- struct protection_domain *pdomain = to_pdomain(domain);
- struct dma_ops_domain *dma_dom = pdomain->priv;
+ struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
unsigned long start, end;
start = IOVA_PFN(region->start);
projects / cascardo / linux.git / blobdiff